# ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning

arXiv: https://arxiv.org/abs/2501.14622 · HTML: https://mlsanity.com/paper/2501.14622/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Latent predictive world models, one of 11 directions in World models.
- Builds on 44 of its 55 references that are in the map.
- First posted on arXiv 24 Jan 2025.

## Placed in

- World models / [Latent predictive world models](https://mlsanity.com/wm/latent-predictive-world-models/)
- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 30 of 44)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [World Models](https://mlsanity.com/paper/1803.10122/) (2018)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning](https://mlsanity.com/paper/1910.10897/) (2019)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Open X-Embodiment: Robotic Learning Datasets and RT-X Models](https://mlsanity.com/paper/2310.08864/) (2023)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [Learning Interactive Real-World Simulators](https://mlsanity.com/paper/2310.06114/) (2023)
- [DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning](https://mlsanity.com/paper/2411.04983/) (2024)
- [Behavior Transformers: Cloning k modes with one stone](https://mlsanity.com/paper/2206.11251/) (2022)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)

## Built on by (most cited first, 8 of 8)

- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [Towards Predictive, Aligned, and Scalable Robot Learning](https://mlsanity.com/paper/2607.11270/) (2026)
- [SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors](https://mlsanity.com/paper/2608.04060/) (2026)
- [The JEPA Predictor: A Transferable Operator for Occluded Feature Completion](https://mlsanity.com/paper/2607.16274/) (2026)
- [WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning](https://mlsanity.com/paper/2608.22591/) (2026)
- [JEPA Policy: Diffusion-Free Imitation Learning via Paired Action and Future Representation Prediction](https://mlsanity.com/paper/2609.09630/) (2026)
- [Mask-Aware Execution for Efficient JEPA Training](https://mlsanity.com/paper/2609.22674/) (2026)
- [Vision-Predictor-Action: Towards Efficient Embodied AI via Neuro-Symbolic JEPA Predictors](https://mlsanity.com/paper/2610.15556/) (2026)

## Abstract (arXiv)

Learning efficient representations for decision-making policies is a challenge in imitation learning (IL). Current IL methods require expert demonstrations, which are expensive to collect. Additionally, they are not explicitly trained to understand the environment. Consequently, they have underdeveloped world models. Self-supervised learning (SSL) offers an alternative, as it can learn a world model from diverse, unlabeled data. However, most SSL methods are inefficient because they operate in raw input space. In this work, we propose ACT-JEPA, a novel architecture that unifies IL and SSL to enhance policy representations. It is trained end-to-end to jointly predict 1) action sequences and 2) latent observation sequences. To learn in latent space, we utilize Joint-Embedding Predictive Architecture, which allows the model to filter out irrelevant details and learn a robust world model. We evaluate ACT-JEPA in different environments and across multiple tasks. Our results show that it outperforms the strongest baseline in all environments. ACT-JEPA achieves up to 40% improvement in world model understanding and up to 10% higher task success rate. Finally, we show that predicting latent observation sequences effectively generalizes to predicting action sequences. This work demonstrates how integrating IL and SSL leads to efficient policy representation learning, an improved world model, and a higher task success rate.